897 citations · 1.2k across the 22 of their papers we have counts for
5 papers · 1 filter
Improving neural network representations using human similarity judgments
Lukas Muttenthaler, Lorenz Linhardt, Jonas Dippel +4
Deep neural networks have reached human-level performance on many computer vision tasks. However, the objectives used to train these networks enforce only that similar images are e…
Human alignment of neural network representations
Lukas Muttenthaler, Jonas Dippel, Lorenz Linhardt +2
Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms diff…
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen +3
Due to the intractability of characterizing everything that looks unlike the normal data, anomaly detection (AD) is traditionally treated as an unsupervised problem utilizing only…
Learning Interpretable Concept Groups in CNNs
Saurabh Varshneya, Antoine Ledent, Robert A. Vandermeulen +4
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept…
Explainable Deep One-Class Classification
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen +3
Deep one-class classification variants for anomaly detection learn a mapping that concentrates nominal samples in feature space causing anomalies to be mapped away. Because this tr…